Thema der Dissertation:
Unsupervised Learning of Molecular Representations for Drug Development Thema der Disputation:
Machine Learning for Molecular Property Prediction and Optimisation in Drug Discovery
Unsupervised Learning of Molecular Representations for Drug Development Thema der Disputation:
Machine Learning for Molecular Property Prediction and Optimisation in Drug Discovery
Abstract: Developing pharmaceutical drug candidates involves a substantial commitment of time and resources. A major task in the early stage of Drug Discovery is finding molecules that have desirable properties (e.g., high binding affinity to the biological target of interest).
In the first part of this talk, I will discuss how Machine Learning can be used to accelerate this process by either predicting such properties for a given molecule or to directly propose novel drug candidates with desirable properties. In the second part I will present the results of my thesis, exploring how Unsupervised Machine Learning can improve such methods by extracting expressive representations of molecular entities.
In the first part of this talk, I will discuss how Machine Learning can be used to accelerate this process by either predicting such properties for a given molecule or to directly propose novel drug candidates with desirable properties. In the second part I will present the results of my thesis, exploring how Unsupervised Machine Learning can improve such methods by extracting expressive representations of molecular entities.
Zeit & Ort
25.08.2023 | 15:00